Explore reusable agentic workflow patterns.
Browse dynamic workflow scripts and operating notes for research, refactoring, security audits, performance checks, and other work that benefits from parallel agents plus explicit verification.
Current launch model
Run inside Claude Code
Parallel phases
Use fan-out only where tasks are independent enough to compare and merge cleanly.
Reviewer loops
Strong workflows make verification explicit before results converge into a final answer.
Local filtering
Search examples by title, description, and tags without leaving the page.
Browse dynamic workflows
Copy, adapt, and inspect workflow patterns contributed by developers around the world.
Claude Code /deep-research Built-in Workflow
MediumDeep research harness — decomposes question into 5 complementary search angles, fans out WebSearch agents, deduplicates URLs and budgets fetches, extracts falsifiable claims, runs 3-vote adversarial verification (need 2/3 refutes to kill), then synthesizes a cited report with confidence levels, caveats, and open questions.
Parallel Test Refactoring and Visualizer
MediumFans out subagents to migrate legacy Jest tests to Vitest in parallel, verifying syntax correctness and running tests at each phase.
Adversarial Codebase Security Audit
HardDeploys one group of agents to scan for vulnerabilities (XSS, SQL Injection, Dependency issues) and another group of adversarial agents trying to exploit the findings to confirm exploits.
LCP & Image Performance Optimizer
EasyAutomated Core Web Vitals audit. Analyzes LCP components, optimizes image formats, adds fetchpriority, and validates layouts.